def get_formatted_scans_key_row(item):
"""
Parameters
----------
item
Returns
-------
row: list
[ISO acquisition time, performing physician name, random string]
"""
dcm_fn = item[-1][0]
mw = ds.wrapper_from_data(dcm.read_file(dcm_fn,
stop_before_pixels=True,
force=True))
# we need to store filenames and acquisition times
# parse date and time and get it into isoformat
date = mw.dcm_data.ContentDate
time = mw.dcm_data.ContentTime.split('.')[0]
td = time + date
acq_time = datetime.strptime(td, '%H%M%S%Y%m%d').isoformat()
# add random string
randstr = ''.join(map(chr, sample(k=8, population=range(33, 127))))
try:
perfphys = mw.dcm_data.PerformingPhysicianName
except AttributeError:
perfphys = ''
row = [acq_time, perfphys, randstr]
# empty entries should be 'n/a'
# https://github.com/dartmouth-pbs/heudiconv/issues/32
row = ['n/a' if not str(e) else e for e in row]
return row
def get_slice_timing(root):
for path, subdirs, files in os.walk(root):
if files:
dcm_files = glob(op.join(path,'*.dcm'))
num_files = len(dcm_files)
slice_time = [None]*num_files
for i in range(num_files):
dcm_fn = dcm_files[i]
dcm_filepath = os.path.join(path, dcm_fn)
mw = ds.wrapper_from_data(dcm.read_file(dcm_filepath,
stop_before_pixels=True,
force=True))
dcminfo = mw.dcm_data
aquision_time = float(dcminfo.TriggerTime)/1000
slice_time[i] = aquision_time
return (slice_time)
else:
print('Nan file path')
def group_dicoms_into_seqinfos(files, file_filter, dcmfilter, grouping):
"""Process list of dicoms and return seqinfo and file group
`seqinfo` contains per-sequence extract of fields from DICOMs which
will be later provided into heuristics to decide on filenames
Parameters
----------
files : list of str
List of files to consider
file_filter : callable, optional
Applied to each item of filenames. Should return True if file needs to be
kept, False otherwise.
dcmfilter : callable, optional
If called on dcm_data and returns True, it is used to set series_id
grouping : {'studyUID', 'accession_number', None}, optional
what to group by: studyUID or accession_number
Returns
-------
seqinfo : list of list
`seqinfo` is a list of info entries per each sequence (some entry
there defines a key for `filegrp`)
filegrp : dict
`filegrp` is a dictionary with files groupped per each sequence
"""
allowed_groupings = ['studyUID', 'accession_number', None]
if grouping not in allowed_groupings:
raise ValueError('I do not know how to group by {0}'.format(grouping))
per_studyUID = grouping == 'studyUID'
per_accession_number = grouping == 'accession_number'
lgr.info("Analyzing %d dicoms", len(files))
import dcmstack as ds
import dicom as dcm
groups = [[], []]
mwgroup = []
studyUID = None
# for sanity check that all DICOMs came from the same
# "study". If not -- what is the use-case? (interrupted acquisition?)
# and how would then we deal with series numbers
# which would differ already
if file_filter:
nfl_before = len(files)
files = list(filter(file_filter, files))
nfl_after = len(files)
lgr.info('Filtering out {0} dicoms based on their filename'.format(
nfl_before - nfl_after))
for fidx, filename in enumerate(files):
# TODO after getting a regression test check if the same behavior
# with stop_before_pixels=True
mw = ds.wrapper_from_data(dcm.read_file(filename, force=True))
for sig in ('iop', 'ICE_Dims', 'SequenceName'):
try:
del mw.series_signature[sig]
except:
pass
try:
file_studyUID = mw.dcm_data.StudyInstanceUID
except AttributeError:
lgr.info(
"File {} is missing any StudyInstanceUID".format(filename))
file_studyUID = None
try:
series_id = (int(mw.dcm_data.SeriesNumber),
mw.dcm_data.ProtocolName)
file_studyUID = mw.dcm_data.StudyInstanceUID
if not per_studyUID:
# verify that we are working with a single study
if studyUID is None:
studyUID = file_studyUID
elif not per_accession_number:
assert studyUID == file_studyUID, (
"Conflicting study identifiers found [{}, {}].".format(
studyUID, file_studyUID))
except AttributeError as exc:
lgr.warning('Ignoring %s since not quite a "normal" DICOM: %s',
filename, exc)
series_id = (-1, 'none')
file_studyUID = None
if not series_id[0] < 0:
if dcmfilter is not None and dcmfilter(mw.dcm_data):
series_id = (-1, mw.dcm_data.ProtocolName)
# filter out unwanted non-image-data DICOMs by assigning
# a series number < 0 (see test below)
if not series_id[0] < 0 and mw.dcm_data[0x0008, 0x0016].repval in (
'Raw Data Storage',
'GrayscaleSoftcopyPresentationStateStorage'):
series_id = (-1, mw.dcm_data.ProtocolName)
if per_studyUID:
series_id = series_id + (file_studyUID, )
ingrp = False
for idx in range(len(mwgroup)):
# same = mw.is_same_series(mwgroup[idx])
if mw.is_same_series(mwgroup[idx]):
# the same series should have the same study uuid
assert (mwgroup[idx].dcm_data.get('StudyInstanceUID',
None) == file_studyUID)
ingrp = True
if series_id[0] >= 0:
series_id = (mwgroup[idx].dcm_data.SeriesNumber,
mwgroup[idx].dcm_data.ProtocolName)
if per_studyUID:
series_id = series_id + (file_studyUID, )
groups[0].append(series_id)
groups[1].append(idx)
if not ingrp:
mwgroup.append(mw)
groups[0].append(series_id)
groups[1].append(len(mwgroup) - 1)
group_map = dict(zip(groups[0], groups[1]))
total = 0
seqinfo = OrderedDict()
# for the next line to make any sense the series_id needs to
# be sortable in a way that preserves the series order
for series_id, mwidx in sorted(group_map.items()):
if series_id[0] < 0:
# skip our fake series with unwanted files
continue
mw = mwgroup[mwidx]
if mw.image_shape is None:
# this whole thing has now image data (maybe just PSg DICOMs)
# nothing to see here, just move on
continue
dcminfo = mw.dcm_data
series_files = [
files[i] for i, s in enumerate(groups[0]) if s == series_id
]
# turn the series_id into a human-readable string -- string is needed
# for JSON storage later on
if per_studyUID:
studyUID = series_id[2]
series_id = series_id[:2]
accession_number = dcminfo.get('AccessionNumber')
series_id = '-'.join(map(str, series_id))
size = list(mw.image_shape) + [len(series_files)]
total += size[-1]
if len(size) < 4:
size.append(1)
# MG - refactor into util function
try:
TR = float(dcminfo.RepetitionTime) / 1000.
except (AttributeError, ValueError):
TR = -1
try:
TE = float(dcminfo.EchoTime)
except (AttributeError, ValueError):
TE = -1
try:
refphys = str(dcminfo.ReferringPhysicianName)
except AttributeError:
refphys = ''
try:
image_type = tuple(dcminfo.ImageType)
except AttributeError:
image_type = ''
try:
series_desc = dcminfo.SeriesDescription
except AttributeError:
series_desc = ''
motion_corrected = 'MOCO' in image_type
if dcminfo.get([0x18, 0x24], None):
# GE and Philips scanners
sequence_name = dcminfo[0x18, 0x24].value
elif dcminfo.get([0x19, 0x109c], None):
# Siemens scanners
sequence_name = dcminfo[0x19, 0x109c].value
else:
sequence_name = 'Not found'
info = SeqInfo(
total,
op.split(series_files[0])[1],
series_id,
op.basename(op.dirname(series_files[0])),
'-',
'-',
size[0],
size[1],
size[2],
size[3],
TR,
TE,
dcminfo.ProtocolName,
motion_corrected,
'derived' in [x.lower() for x in dcminfo.get('ImageType', [])],
dcminfo.get('PatientID'),
dcminfo.get('StudyDescription'),
refphys,
dcminfo.get('SeriesDescription'),
sequence_name,
image_type,
accession_number,
# For demographics to populate BIDS participants.tsv
dcminfo.get('PatientAge'),
dcminfo.get('PatientSex'),
dcminfo.get('AcquisitionDate'),
)
# candidates
# dcminfo.AccessionNumber
# len(dcminfo.ReferencedImageSequence)
# len(dcminfo.SourceImageSequence)
# FOR demographics
if per_studyUID:
key = studyUID.split('.')[-1]
elif per_accession_number:
key = accession_number
else:
key = ''
lgr.debug(
"%30s %30s %27s %27s %5s nref=%-2d nsrc=%-2d %s" %
(key, info.series_id, dcminfo.SeriesDescription,
dcminfo.ProtocolName, info.is_derived,
len(dcminfo.get('ReferencedImageSequence', '')),
len(dcminfo.get('SourceImageSequence', '')), info.image_type))
if per_studyUID:
if studyUID not in seqinfo:
seqinfo[studyUID] = OrderedDict()
seqinfo[studyUID][info] = series_files
elif per_accession_number:
if accession_number not in seqinfo:
seqinfo[accession_number] = OrderedDict()
seqinfo[accession_number][info] = series_files
else:
seqinfo[info] = series_files
if per_studyUID:
lgr.info(
"Generated sequence info for %d studies with %d entries total",
len(seqinfo), sum(map(len, seqinfo.values())))
elif per_accession_number:
lgr.info(
"Generated sequence info for %d accession numbers with %d "
"entries total", len(seqinfo), sum(map(len, seqinfo.values())))
else:
lgr.info("Generated sequence info with %d entries", len(seqinfo))
return seqinfo
def process_dicoms(fl):
groups = [[], []]
mwgroup = []
hays = open("/scratch/PSB6351_2017/week4/hays/debug1.txt", 'w')
hays.write("Here\n")
hays.flush()
for fidx, filename in enumerate(fl):
mw = ds.wrapper_from_data(dcm.read_file(filename, force=True))
try:
del mw.series_signature['iop']
except:
pass
try:
del mw.series_signature['ICE_Dims']
except:
pass
try:
del mw.series_signature['SequenceName']
except:
pass
if not groups:
if hasattr(mw.dcm_data, 'SeriesNumber'):
mwgroup.append(mw)
groups[0].append(int(mw.dcm_data.SeriesNumber))
groups[1].append(len(mwgroup) - 1)
continue
N = len(mwgroup)
#print fidx, N, filename
ingrp = False
for idx in range(N):
same = mw.is_same_series(mwgroup[idx])
#print idx, same, groups[idx][0]
if same:
if hasattr(mw.dcm_data, 'SeriesNumber'):
groups[0].append(int(mwgroup[idx].dcm_data.SeriesNumber))
groups[1].append(idx)
ingrp = True
if not ingrp:
if hasattr(mw.dcm_data, 'SeriesNumber'):
mwgroup.append(mw)
groups[0].append(int(mw.dcm_data.SeriesNumber))
groups[1].append(len(mwgroup) - 1)
group_map = dict(zip(groups[0], groups[1]))
if 20002 in group_map.keys():
group_map.pop(20002, None)
if 20004 in group_map.keys():
group_map.pop(20004, None)
if 300 in group_map.keys():
group_map.pop(300, None)
if 301 in group_map.keys():
group_map.pop(301, None)
if 302 in group_map.keys():
group_map.pop(302, None)
total = 0
filegroup = {}
seqinfo = []
for series, mwidx in sorted(group_map.items()):
mw = mwgroup[mwidx]
dcminfo = mw.dcm_data
files = np.array(fl)[np.array(groups[0]) == series].tolist()
filegroup[series] = files
size = list(mw.image_shape) + [dcminfo.ImagesinAcquisition]
total += size[-1]
if hasattr(dcminfo, 'NumberofTemporalPositions'):
size.append(dcminfo.NumberofTemporalPositions)
else:
size.append(1)
try:
TR = float(dcminfo.RepetitionTime)/1000.
except AttributeError:
TR = -1
try:
TE = float(dcminfo.EchoTime)
except AttributeError:
TE = -1
hays.write("Total: {0}\n".format(total))
hays.write("series: {0}\n".format(series))
hays.write("Split Path: {0}\n".format(os.path.split(files[0])[1]))
hays.write("dcminfo.SeriesDescription: {0}\n".format(dcminfo.SeriesDescription))
hays.write("size: {0}\n".format(size))
hays.write("TR: {0}\n".format(TR))
info = [total, os.path.split(files[0])[1], series, '-', '-', '-'] + \
size + [TR, TE, dcminfo.SeriesDescription]
seqinfo.append(info)
hays.write(str(seqinfo))
hays.flush()
hays.close()
return seqinfo, filegroup
def process_dicoms(fl):
groups = [[], []]
mwgroup = []
for fidx, filename in enumerate(fl):
mw = ds.wrapper_from_data(dcm.read_file(filename, force=True))
try:
del mw.series_signature['iop']
except:
pass
try:
del mw.series_signature['ICE_Dims']
except:
pass
try:
del mw.series_signature['SequenceName']
except:
pass
if not groups:
mwgroup.append(mw)
groups[0].append(int(mw.dcm_data.SeriesNumber))
groups[1].append(len(mwgroup) - 1)
continue
N = len(mwgroup)
#print fidx, N, filename
ingrp = False
for idx in range(N):
same = mw.is_same_series(mwgroup[idx])
#print idx, same, groups[idx][0]
if same:
groups[0].append(int(mwgroup[idx].dcm_data.SeriesNumber))
groups[1].append(idx)
ingrp = True
if not ingrp:
mwgroup.append(mw)
groups[0].append(int(mw.dcm_data.SeriesNumber))
groups[1].append(len(mwgroup) - 1)
group_map = dict(zip(groups[0], groups[1]))
if 5001 in group_map.keys():
group_map.pop(5001, None)
total = 0
filegroup = {}
seqinfo = []
for series, mwidx in sorted(group_map.items()):
mw = mwgroup[mwidx]
dcminfo = mw.dcm_data
files = np.array(fl)[np.array(groups[0]) == series].tolist()
filegroup[series] = files
size = list(mw.image_shape) + [len(files)]
total += size[-1]
if len(size) < 4:
size.append(1)
try:
TR = float(dcminfo.RepetitionTime) / 1000.
except AttributeError:
TR = -1
try:
TE = float(dcminfo.EchoTime)
except AttributeError:
TE = -1
info = [total, os.path.split(files[0])[1], series, '-', '-', '-'] + \
size + [TR, TE, dcminfo.ProtocolName, 'MoCo' in dcminfo.SeriesDescription]
seqinfo.append(info)
return seqinfo, filegroup
def get_scan_info(root, basedir):
"""
Parameters:
item
---------------------------------------------------------------------------
Returns:
row: list
[ISO acquisition time, performing physician name, random string]
"""
for path, subdirs, files in os.walk(root):
if path.split('_')[-1] == 'dicoms' and "Save" not in re.split(r'[_|@|/]', path) \
and "calibration" not in re.split(r'[_|@|/]', path) \
and "Loc" not in re.split(r'[_|@|/]', path) \
and "Processed" not in re.split(r'[_|@|/]', path):
if files:
niiDir = path.replace(path.split('/')[-1], "").replace('untar', 'raw')
niifiles = glob(os.path.join(niiDir, '*.nii.gz'))
dcm_files = glob(op.join(path,'*.dcm'))
dcm_fn = dcm_files[0]
dcm_filepath = os.path.join(path, dcm_fn)
mw = ds.wrapper_from_data(dcm.read_file(dcm_filepath,
stop_before_pixels=True,
force=True))
dcminfo = mw.dcm_data
# MG
try:
TR = float(dcminfo.RepetitionTime) / 1000.
except (AttributeError, ValueError):
TR = -1
try:
TE = float(dcminfo.EchoTime)
except (AttributeError, ValueError):
TE = -1
projectName = re.split(r'[_|@|/]', dcminfo.PatientID)[-1]
projectPath = os.path.join(basedir, projectName)
mkdir(projectPath)
targetPath = os.path.join(projectPath, 'source')
mkdir(targetPath)
date = dcminfo.ContentDate
time = dcminfo.ContentTime.split('.')[0]
td = time + date
acq_time = datetime.strptime(td, '%H%M%S%Y%m%d').isoformat()
key_subID = date
if key_subID in dict_subID.keys():
info_subID = dict_subID[key_subID]
subPrefix = info_subID
subID = re.split(r'[_]', info_subID)[0].split('-')[1]
subDir = os.path.join(targetPath, 'sub-'+subID)
mkdir(subDir)
phase = re.split(r'[_]', info_subID)[1].split('-')[1]
secDir = os.path.join(subDir, 'ses-'+phase)
mkdir(secDir)
else:
print('no such key')
subID = re.split(r'[_|@|/]', dcminfo.PatientID)[0].split('s')[-1]
subDir = os.path.join(targetPath, subID)
mkdir(subDir)
phase = re.split(r'[_|@|/]', dcminfo.PatientID)[1]
secDir = os.path.join(subDir, subID)
mkdir(secDir)
subPrefix = 'sub-'+subID+'_ses-'+phase
subAge = int(dcminfo.PatientAge.split('Y')[0])
subSex = dcminfo.PatientSex
#scanType = re.split(r'[\s]', dcminfo.SeriesDescription)[0]
scanType = dcminfo[0x19109e].value
# Fieldmap; EffectiveEchoSpacing and TotalReadoutTime
ETL = dcminfo.EchoTrainLength
PEbandwidth = float(dcminfo.PixelBandwidth)
ACCFactor = 3#have not figure out how to read directlly from dcm. right now read from nii header
#EffectiveEchoSpacing = 1 / (PEbandwidth * (ETL - 1) * ACCFactor)
#TotalReadoutTime = 1/PEbandwidth
taskName = dcminfo.SeriesDescription.split(' ')[0]
#Build the info dics and save them
Dataset_Description = dict()
Dataset_Description['Name'] = projectName
Dataset_Description['BIDSVersion'] = BIDSVersion
Dataset_Description['License'] = License
Dataset_Description['Authors'] = Authors
Dataset_Description['Acknowledgements'] = Acknowledgements
Dataset_Description['HowToAcknowledge'] = HowToAcknowledge
Dataset_Description['Funding'] = Funding
Dataset_Description['InstitutionName'] = dcminfo.InstitutionName
Dataset_Description['Manufacturer'] = dcminfo.Manufacturer
Dataset_Description['ManufacturersModelName'] = dcminfo.ManufacturersModelName
fname = os.path.join(targetPath, 'dataset_description.json')
write_json(fname, Dataset_Description, 'TRUE')
#Dataset_Description['Session'] = phase
Dataset_Description['SubID'] = subID
Dataset_Description['SubAge'] = subAge
Dataset_Description['SubSex'] = subSex
fname = os.path.join(subDir, 'dataset_description.json')
write_json(fname, Dataset_Description, 'TRUE')
if scanType == 'EFGRE3D':
Anatomy_Info = dict()
Anatomy_Info['ScanType'] = 'T1'
Anatomy_Info['SeriesDescription'] = dcminfo.SeriesDescription
Anatomy_Info['AcquisitionMatrix'] = dcminfo.AcquisitionMatrix
Anatomy_Info['RepetitionTime'] = TR
Anatomy_Info['TE'] = TE
Anatomy_Info['FlipAngle'] = int(dcminfo.FlipAngle)
Anatomy_Info['InstitutionName'] = dcminfo.InstitutionName
Anatomy_Info['Manufacturer'] = dcminfo.Manufacturer
Anatomy_Info['ManufacturersModelName'] = dcminfo.ManufacturersModelName
Anatomy_Info['AcqTime'] = acq_time
anatdir = os.path.join(secDir, 'anat')
mkdir(anatdir)
for i in niifiles:
copy(i, os.path.join(anatdir, subPrefix+'_T1w.nii.gz'))
fname = os.path.join(anatdir, subPrefix+'_T1w.json')
write_json(fname, Anatomy_Info, 'TRUE')
elif scanType == '3DFSE':
Anatomy_Info = dict()
Anatomy_Info['ScanType'] = 'T2'
Anatomy_Info['SeriesDescription'] = dcminfo.SeriesDescription
Anatomy_Info['AcquisitionMatrix'] = dcminfo.AcquisitionMatrix
Anatomy_Info['RepetitionTime'] = TR
Anatomy_Info['TE'] = TE
Anatomy_Info['FlipAngle'] = int(dcminfo.FlipAngle)
Anatomy_Info['InstitutionName'] = dcminfo.InstitutionName
Anatomy_Info['Manufacturer'] = dcminfo.Manufacturer
Anatomy_Info['ManufacturersModelName'] = dcminfo.ManufacturersModelName
Anatomy_Info['AcqTime'] = acq_time
anatdir = os.path.join(secDir, 'anat')
mkdir(anatdir)
for i in niifiles:
copy(i, os.path.join(anatdir, subPrefix+'_T2w.nii.gz'))
fname = os.path.join(anatdir, subPrefix+'_T2w.json')
write_json(fname, Anatomy_Info, 'TRUE')
elif scanType == 'EPI':
slice_times = get_slice_timing(root)
Func_Info = dict()
Func_Info['ScanType'] = 'Func'
Func_Info['SeriesDescription'] = dcminfo.SeriesDescription
Func_Info['AcquisitionMatrix'] = dcminfo.AcquisitionMatrix
Func_Info['RepetitionTime'] = TR
Func_Info['TE'] = TE
Func_Info['FlipAngle'] = int(dcminfo.FlipAngle)
Func_Info['SliceTiming'] = slice_times
Func_Info['ACCFactor'] = ACCFactor
Func_Info['InstitutionName'] = dcminfo.InstitutionName
Func_Info['Manufacturer'] = dcminfo.Manufacturer
Func_Info['ManufacturersModelName'] = dcminfo.ManufacturersModelName
Func_Info['AcqTime'] = acq_time
Func_Info['TaskName'] = taskName
funcdir = os.path.join(secDir, 'func')
mkdir(funcdir)
for i in niifiles:
copy(i, os.path.join(funcdir, subPrefix+'_task-'+taskName+'_bold.nii.gz'))
fname = os.path.join(funcdir, subPrefix+'_task-'+taskName+'_bold.json')
write_json(fname, Func_Info, 'TRUE')
elif scanType == 'Fieldmap':
Fieldmap_Info = dict()
Fieldmap_Info['ScanType'] = 'Fieldmap'
Fieldmap_Info['SeriesDescription'] = dcminfo.SeriesDescription
Fieldmap_Info['AcquisitionMatrix'] = dcminfo.AcquisitionMatrix
Fieldmap_Info['RepetitionTime'] = TR
Fieldmap_Info['TE'] = TE
Fieldmap_Info['FlipAngle'] = int(dcminfo.FlipAngle)
Fieldmap_Info['ACCFactor'] = ACCFactor
Fieldmap_Info['EffectiveEchoSpacing'] = EffectiveEchoSpacing
Fieldmap_Info['phaseEncodeDirection'] = phaseEncodeDirection
Fieldmap_Info['InstitutionName'] = dcminfo.InstitutionName
Fieldmap_Info['Manufacturer'] = dcminfo.Manufacturer
Fieldmap_Info['ManufacturersModelName'] = dcminfo.ManufacturersModelName
Fieldmap_Info['AcqTime'] = acq_time
fpdir = os.path.join(secDir, 'fmap')
mkdir(fpdir)
for i in niifiles:
copy(i, os.path.join(fpdir, subPrefix+'_fmap.nii.gz'))
fname = os.path.join(fpdir, subPrefix+'_fmap.json')
write_json(fname, Fieldmap_Info, 'TRUE')
def sort_rule_clinical(filename, args):
'''
Clinical sort rule:
patient_name
|-study_date
|-modality
|-series_number
|-{patient}.{modality}.{series:04d}.{image:04d}.{study_date}.{unique}.dcm
...
|-series_number
...
intput:
filename: dicom filename
output:
a dictionary:
key: filename
value: patient_name/study_date/modality/sereis_number/{patient}.{modality}.{series:04d}.{image:04d}.{study_date}.{unique}.dcm
'''
def write_error_file(filen, errorInfoTemp):
if os.path.exists(filen):
with open(filen, 'r') as readFile:
reader = csv.reader(readFile, delimiter='\t')
lines = list(reader)
if errorInfoTemp.split('\t') not in lines:
with open(filen, 'a') as writeFile:
writeFile.write(errorInfoTemp)
writeFile.write("\n")
else:
with open(filen, 'w') as writeFile:
writeFile.write(
"\t".join(['subject', 'date', 'series', 'issue']))
writeFile.write("\n")
writeFile.write(errorInfoTemp)
writeFile.write("\n")
def clean_path(path):
return re.sub(r'[^a-zA-Z0-9.-]', '_', '{0}'.format(path))
def hashcode(value):
code = 0
for character in value:
code = (code * 31 + ord(character)) & 0xffffffff
return '{0:08X}'.format(code)
# This will ignore any dicomdir present in the folder
if all(['DICOMDIR' not in filename, not filename.endswith('OR_dates.tsv')]):
logger = logging.getLogger(__name__)
try:
error_file = os.path.join(args.dicom_dir, 'errorInfo.tsv')
or_dates_file = os.path.join(args.dicom_dir, 'or_dates.tsv')
dataset = pydicom.read_file(
filename, stop_before_pixels=True, force=True)
study_date = dataset.StudyDate[0:4] + '_' + \
dataset.StudyDate[4:6] + '_' + dataset.StudyDate[6:8]
if 'SeriesDescription' in dataset:
if any(x in dataset.SeriesDescription.upper() for x in {'REJECTION'}):
return None
# This will skip any order sheets
if dataset.Modality in {'SR', 'PR', 'KO'}:
errorInfoTemp = "\t".join(['P' + [s for s in filename.split(os.sep) if 'sub' in s][0].split('-')[1], study_date,
clean_path('{series:04d}'.format(series=dataset.SeriesNumber)), dataset.Modality])
write_error_file(error_file, errorInfoTemp)
return None
# This will skip any order sheets and localizers
elif 'ImageType' not in dataset:
return None
elif any(x in dataset.ImageType for x in {'SECONDARY', 'LOCALIZER'}):
return None
else:
if 'Manufacturer' in dataset:
if 'SIEMENS' in dataset.Manufacturer:
errorInfoTemp = "\t".join(['P' + [s for s in filename.split(os.sep) if 'sub' in s][0].split('-')[1], study_date,
clean_path('{series:04d}'.format(series=dataset.SeriesNumber)), 'SIEMENS'])
write_error_file(error_file, errorInfoTemp)
return None
try:
csaReader = ds.wrapper_from_data(dataset)
modality = dataset.Modality
# --- INTRAOP X-RAY determination
if any(substring in modality for substring in {'Intraoperative', 'Skull', 'XA', 'RF','CR','OT'}):
if 'CR' not in dataset.Modality:
or_date = dataset.StudyDate[0:4] + '_' + \
dataset.StudyDate[4:6] + \
'_' + dataset.StudyDate[6:8]
orDateTemp = "\t".join(
['P' + [s for s in filename.split(os.sep) if 'sub' in s][0].split('-')[1], or_date])
if os.path.exists(or_dates_file):
with open(or_dates_file, 'r') as readFile:
reader = csv.reader(
readFile, delimiter='\t')
lines = list(reader)
if orDateTemp.split('\t') not in lines:
with open(or_dates_file, 'a') as writeFile:
writeFile.write(orDateTemp)
writeFile.write("\n")
else:
with open(or_dates_file, 'w') as writeFile:
writeFile.write(
"\t".join(['subject', 'or_date']))
writeFile.write("\n")
writeFile.write(orDateTemp)
writeFile.write("\n")
return None
elif all(['CR' in dataset.Modality, any(x in dataset.StudyDescription for x in {'Skull Routine Portable', 'Intraoperative Portable'})]):
errorInfoTemp = "\t".join(['P' + [s for s in filename.split(os.sep) if 'sub' in s][0].split('-')[1], study_date,
clean_path('{series:04d}'.format(series=dataset.SeriesNumber)), dataset.StudyDescription])
write_error_file(error_file, errorInfoTemp)
return None
else:
patient = 'P' + \
[s for s in filename.split(os.sep) if 'sub' in s][0].split(
'-')[1] + '_' + study_date
series_number = clean_path(
'{series:04d}'.format(series=dataset.SeriesNumber))
studyID_and_hash_studyInstanceUID = clean_path('.'.join([dataset.StudyID or 'NA',
hashcode(dataset.StudyInstanceUID)]))
path = os.path.join(
patient, dataset.StudyDate, studyID_and_hash_studyInstanceUID, modality, series_number)
sorted_filename = '{patient}.{modality}.{series:04d}.{image:04d}.{study_date}.{unique}.dcm'.format(
patient=patient.upper(),
modality=modality,
series=dataset.SeriesNumber,
image=dataset.InstanceNumber,
study_date=dataset.StudyDate,
unique=hashcode(dataset.SOPInstanceUID),
)
else:
if dataset.SeriesDescription.lower() not in {'loc', 'dose report'}:
patient = 'P' + \
[s for s in filename.split(os.sep) if 'sub' in s][0].split(
'-')[1] + '_' + study_date
series_number = clean_path(
'{series:04d}'.format(series=dataset.SeriesNumber))
studyID_and_hash_studyInstanceUID = clean_path('.'.join([dataset.StudyID or 'NA',
hashcode(dataset.StudyInstanceUID)]))
path = os.path.join(
patient, dataset.StudyDate, studyID_and_hash_studyInstanceUID, modality, series_number)
sorted_filename = '{patient}.{modality}.{series:04d}.{image:04d}.{study_date}.{unique}.dcm'.format(
patient=patient.upper(),
modality=modality,
series=dataset.SeriesNumber,
image=dataset.InstanceNumber,
study_date=dataset.StudyDate,
unique=hashcode(dataset.SOPInstanceUID),
)
except Exception as e:
errorInfoTemp = "\t".join(['P' + [s for s in filename.split(os.sep) if 'sub' in s][0].split('-')[1], study_date,
clean_path('{series:04d}'.format(series=dataset.SeriesNumber)), 'csaReader'])
write_error_file(error_file, errorInfoTemp)
return None
except Exception as e:
logger.exception('something wrong with {}'.format(filename))
logger.exception(e)
return None
if 'path' in locals():
sorted_full_filename = os.path.join(path, sorted_filename)
return sorted_full_filename
else:
return None
def process_dicoms(fl):
groups = [[], []]
mwgroup = []
for fidx, filename in enumerate(fl):
mw = ds.wrapper_from_data(dcm.read_file(filename, force=True))
try:
del mw.series_signature['iop']
except:
pass
try:
del mw.series_signature['ICE_Dims']
except:
pass
try:
del mw.series_signature['SequenceName']
except:
pass
if not groups:
if hasattr(mw.dcm_data, 'SeriesNumber'):
mwgroup.append(mw)
groups[0].append(int(mw.dcm_data.SeriesNumber))
groups[1].append(len(mwgroup) - 1)
continue
N = len(mwgroup)
#print fidx, N, filename
ingrp = False
for idx in range(N):
same = mw.is_same_series(mwgroup[idx])
#print idx, same, groups[idx][0]
if same:
if hasattr(mw.dcm_data, 'SeriesNumber'):
groups[0].append(int(mwgroup[idx].dcm_data.SeriesNumber))
groups[1].append(idx)
ingrp = True
if not ingrp:
if hasattr(mw.dcm_data, 'SeriesNumber'):
mwgroup.append(mw)
groups[0].append(int(mw.dcm_data.SeriesNumber))
groups[1].append(len(mwgroup) - 1)
group_map = dict(zip(groups[0], groups[1]))
if 20002 in group_map.keys():
group_map.pop(20002, None)
if 300 in group_map.keys():
group_map.pop(300, None)
total = 0
filegroup = {}
seqinfo = []
for series, mwidx in sorted(group_map.items()):
mw = mwgroup[mwidx]
dcminfo = mw.dcm_data
files = np.array(fl)[np.array(groups[0]) == series].tolist()
filegroup[series] = files
size = list(mw.image_shape) + [dcminfo.ImagesinAcquisition]
total += size[-1]
if hasattr(dcminfo, 'NumberofTemporalPositions'):
size.append(dcminfo.NumberofTemporalPositions)
else:
size.append(1)
try:
TR = float(dcminfo.RepetitionTime)/1000.
except AttributeError:
TR = -1
try:
TE = float(dcminfo.EchoTime)
except AttributeError:
TE = -1
info = [total, os.path.split(files[0])[1], series, '-', '-', '-'] + \
size + [TR, TE, dcminfo.SeriesDescription]
seqinfo.append(info)
return seqinfo, filegroup